A high-precision ellipse detection method based on quadrant representation and top-down fitting

Abstract

Ellipse detection is a basic task in many computer-vision related problems. While widely studied in recent years, accurate and efficient detection in real-world images is still a challenge. In this paper, a novel ellipse detector, with high accuracy and efficiency, is proposed. The detector models edge by block sequences, and extracts a set of elliptical arcs, which are classified into four sets. Then top-down ellipse fitting strategy that also makes the method able to detect small and flat ellipses is designed. A two-level validation process is used to select highly probable potential ellipses, especially for fragmented ellipses. Experiments on four synthetic datasets show that the proposed method performs far better than existing methods. In images with severe cluttering and occlusion, the F-measure can still be around 0.9. On four real image datasets the proposed method achieves better F-measure scores with competitive speed than state-of-the-art techniques.